For everyone tired of the loop

You've rewritten the same prompt
thirty times this month.

There's a reason it never compounds.

Prompts are oral tradition. We made them software. Authorable, versionable, testable, composable. The first medium you've had where yesterday's work compounds into tomorrow's.

Free · No credit card · Built by one founder out of Toledo

Live · 0 setup · 0 signup

See the difference yourself

Pick an input. Press the button. Watch a generic prompt and a Brainboot brain stream side-by-side. The contrast is the entire pitch.

Try with:
Input · 3,000-word essay on the 2021 Texas power grid failure
On February 11, 2021, a winter storm began moving south across the United States. Within four days the Electric Reliability Council of Texas would order rolling blackouts that left 4.5 million homes without power, killed at least 246 people, and caused over $195 billion in damages. The story most often told blames the cold. But the real cause traces back to a 1999 deregulation vote and decades of avoided weatherization investment... [2,800 more words]
Generic prompt: "summarize this"
Output will appear here when you press Run.
Editor TL;DR brain · 3 rules · haiku-4.5
Output will appear here when you press Run.
Real outputs captured from claude-haiku-4.5. No API call on this page - instant, infinite, free.
Sound familiar

A week with LLMs, honestly described

You write a prompt that works once. You don't remember exactly what was special about it. Tomorrow you write something close, and the output is worse, and you cannot tell why.

You buy a prompt pack because it looks like leverage. You paste one. It produces something fine. You never use it again.

You build a workflow inside ChatGPT. Three weeks later it stops behaving. You assume the model changed. Maybe it did. You cannot prove it.

You find a thread on X with a "magic prompt." You try it. It is fine. You wonder if the person who posted it tested it more than once.

At the end of every month, you have spent more hours with an LLM than the month before, and you cannot point at a single artifact you built that you trust enough to depend on.

That is not a skill problem.

That is an artifact problem.

You have been trying to do engineering work in a medium that has no engineering surface. Nothing to inspect. Nothing to version. Nothing to test. No way for yesterday's good output to become a building block for tomorrow.

A different artifact fixes everything downstream of it.

The new artifact

A brain. Five parts. All editable.

This is what replaces the prompt in your workflow. The first time you author one, the loop ends.

01

System prompt

Identity. Who the brain is, what it knows, how it talks. A job description, not a spell.

02

Execution rules

Constraints enforced on every run. Atomic. Testable. The wrapper checks these before returning output.

03

Output format

How results come back. Markdown, JSON, code, structured. Shape constrains the model toward useful results.

04

Model + tuning

Cheap models for volume. Flagship for hard reasoning. Lower temperature when consistency matters.

05

Domain protocols

Optional. Named procedures the brain runs when input matches a domain. One brain, multiple input shapes.

00

Versioned, by default

Every change is recorded. Every run is reproducible. You can roll back. You can fork. You can A/B.

One brain, end-to-end

Predictable shape, every run

The brain// editor.tldr
system_prompt
You are a ruthless senior editor. Compress any input to a five-bullet TL;DR. Each bullet is one short sentence. Lead with the most surprising fact, not the topic. Never include throat-clearing.
execution_rules
  • Exactly five bullets, no more, no fewer.
  • No bullet exceeds 18 words.
  • No bullet starts with the word "The".
model: claude-haiku-4.5
temp: 0.4
What it produces// run_001 on a 3,000-word essay
* A single deregulation vote in 1999 made the rest of the failure inevitable.
* Texas runs an isolated grid specifically to escape federal weatherization rules.
* Wind turbines failed last; gas plants failed first by a five-to-one margin.
* Fatalities came mostly from carbon monoxide poisoning, not cold exposure.
* Grid operator board members lived out of state during the event.
Run the same brain on a different essay and you get five new bullets in the same shape. That predictability is what the rules buy you.
What changes

From prompter to engineer

Before
  • ·Scrolling prompt marketplaces hoping to recognize a magic combination of words.
  • ·Re-typing similar prompts day after day because nothing was reusable.
  • ·Blaming yourself when an output disappoints. Editing word order. Re-running.
  • ·Throwing away a working prompt because you forgot to save it somewhere.
  • ·Telling people LLMs are powerful while privately suspecting you are doing it wrong.
After
  • Opening the editor. Editing the rule that failed. Re-running. Watching it pass.
  • Stacking new brains on top of brains you already trust. Yesterday compounds into today.
  • Knowing exactly which constraint fired or did not, when an output is wrong.
  • Forking someone else's brain, tightening one rule, shipping a better version.
  • Doing in fifteen minutes what used to take half a day, and being able to prove it.

What the medium actually buys you

Reproducibility

Same input, same shape of output, every run. The thing that worked yesterday works today, on every model the brain is allowed to use.

Compounding

Yesterday's brain becomes today's component. Tomorrow's blueprint composes three of them. Effort accumulates instead of evaporating.

Honesty

When a brain disappoints, you can see exactly which rule fired or did not. You stop guessing. You debug like you would any other software.

Pricing

Pick where you are right now

Try the medium

Free

$0

Author your first brain. Run it on cheap models. See if the loop breaks for you.

  • 10K tokens / month
  • Haiku-tier models
  • Full editor + marketplace
Most pick this
Author seriously

Pro

$29 / mo
7-day trial · no credit card

The plan for people who plan to actually depend on the brains they write.

  • 1M tokens / month
  • Every model. Opus, GPT-5, o3.
  • Versioning, tracing, invariants
Build with your people

Team

$99 / mo

Shared brain library. Shared budget. The whole team building on the same artifacts.

  • 10M tokens / month, shared
  • Org-wide context fabric
  • Role-based access

30-day refund · indie-built · founder reads every support email

Author your first brain

It takes about ten minutes. The first one is the only one that ever feels hard.

Or, if you cannot face a blank editor today: describe what you want and we will build the brain for you.